Loomem

by vvooki-sys

214 downloads

Not rated

GitHub

Other

About

Open-source context layer for LLM agents — a single Rust binary over MCP with local-first memory, hybrid retrieval, and bitemporal facts. No external database.

Details

Author: vvooki-sys
Downloads: 214
Categories: Other

- One binary with no external services or databases.
- 14 memory_* MCP tools over streamable HTTP.
- Local-first and offline with on-device ONNX embeddings.
- Hybrid retrieval: BM25 + vector + entity-graph weighted fusion.
- Bitemporal facts: distinguishes when a fact was learned vs. when it happened.
- Background consolidation (“dreaming”) merges facts, resolves contradictions, and decays stale entries.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Loomem

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

From the repository

Install the binary with the install script, then run loomem-server from the ~/.loomem directory. Connect any MCP client, for example Claude, with claude mcp add --transport http loomem http://localhost:3030/mcp.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "loomem": {
            "loomem": {
                "command": "loomem-cli",
                "args": [
                    "mcp-stdio",
                    "--url",
                    "http://127.0.0.1:3030"
                ]
            }
        }
    }
}

McpServers

{
    "loomem": {
        "command": "loomem-cli",
        "args": [
            "mcp-stdio",
            "--url",
            "http://127.0.0.1:3030"
        ]
    }
}

Loomem

Open-source context layer for LLM agents — a single Rust binary served over MCP that feeds Claude, ChatGPT, Codex, or any MCP client the facts, decisions, and history they need. Local-first, with no external database.

What it does

- One binary, no external services — RocksDB + Tantivy embedded; no separate vector or graph database to run. - MCP-native — 14 memory_* tools over streamable HTTP. - Local-first & offline — on-device ONNX embeddings; your first entry needs no internet. - Hybrid retrieval — BM25 + vector + entity-graph, weighted fusion. - Bitemporal facts — when a fact was learned vs when it actually happened. - Background consolidation ("dreaming") — merges facts, resolves contradictions, lets stale ones decay. - Apache-2.0, written in Rust.

Install & connect

curl -fsSL https://raw.githubusercontent.com/vvooki-sys/loomem/main/install.sh | sh cd ~/.loomem && loomem-server claude mcp add --transport http loomem http://localhost:3030/mcp

Links

- Website: https://loomem.ai - Compare (vs Mem0 / Zep / Letta / cognee): https://loomem.ai/compare.html - Benchmarks: https://loomem.ai/benchmarks.html - GitHub: https://github.com/vvooki-sys/loomem

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

Loomem

What it does

Install & connect

Links

Install

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive

Reactive Resume

FastMCP v2 🚀